Method of Coalescing Information About Inspected Objects

• US 20080247635A1
• Filed: 10/19/2007
• Published: 10/09/2008
• Est. Priority Date: 03/20/2006
• Status: Active Grant

• Current Assignee: Siemens Energy Incorporated (Siemens AG)
• Original Assignee: Siemens Power Generation, Inc.
• Inventors: Zhang, Xiang, Genc, Yakup, Shannon, Robert E., Davis, Fredrick M.
• Granted Patent: US 8,244,025 B2
• Time in Patent Office: Days
• US Class Current: 382/152
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06T 19/00 Manipulating 3D models or images for computer graphics
• CPC Class Codes: G06T 2200/24 involving graphical user interfaces [GUIs]
• CPC Class Codes: G06T 2207/10012 Stereo images
• CPC Class Codes: G06T 2207/30164 Workpiece; Machine component
• CPC Class Codes: G06T 2219/028 Multiple view windows (top-side-front-sagittal-orthogonal)
• CPC Class Codes: G06T 7/75 involving models

Abstract

A method of coalescing information about inspected objects. The method includes acquiring an image set of an object to be inspected, the image set having a three-dimensional model of the object and a plurality of two-dimensional images of the object. A location of interest is identified on a surface of the modeled object and global coordinate points of the three-dimensional model are designated that characterize the location of interest of the modeled object. A markup tag annotating the location of interest is associate with the designated global coordinate points of the three-dimensional model, and the markup tag is conveyed when viewing any one of the plurality of two-dimensional images of the image set that have at least one image point that correlates to a corresponding designated global coordinate point of the three-dimensional model that characterize the location of interest.

Claims

1. A method of coalescing information about inspected objects comprising:

acquiring an image set of an object to be inspected, said image set having a three-dimensional model of said object and a plurality of two-dimensional images of said object;

identifying a location of interest on a surface of said modeled object;

designating global coordinate points of said three-dimensional model that characterize said location of interest of said modeled object;

creating a markup tag of information that annotates said location of interest;

associating said markup tag with said designated global coordinate points of said three-dimensional model; and

conveying said markup tag when viewing any one of said plurality of two-dimensional images of said image set that have at least one image point that correlates to a corresponding designated global coordinate point of said three-dimensional model that characterize said location of interest.

2. The method of claim 1, wherein correspondence of points between said three-dimensional model and said two-dimensional images are defined by range maps comprising range data correlated to respective points on said three-dimensional model.

3. The method of claim 2, wherein said range data comprises a one-to-one correspondence between image points in each said range map and a respective two-dimensional image.

4. The method of claim 3, wherein said range data comprises surface location and depth information identified with each image point in said two-dimensional images.

5. The method of claim 2, including the step of verifying the visibility of said at least one image point on said two-dimensional image in said three-dimensional model by mapping said at least one image point back to said three-dimensional model, wherein correspondence between said at least one image point and a point on said three-dimensional model verifies visibility of said at least one image point.

6. The method of claim 2, including the step of creating range data for an area of any one of said two-dimensional images that is missing range data.

7. The method of claim 6, wherein said step of creating range data comprises projecting rays from one or more points of origin on one of said two-dimensional images to said three-dimensional model and computing intersection points of said one or more projected rays with said three-dimensional model.

8. The method of claim 7, wherein said step of creating range data further comprises, for any one of said rays, identifying two or more intersection points between said ray and said three-dimensional model, and determining a closest intersection point to the point of origin of said ray as a global coordinate point corresponding to said point of origin on said two-dimensional image.

9. The method of claim 2, including the step of performing image compression on said two-dimensional images including first removing background information and removing information where range data is missing.

10. The method of claim 1, including the step of performing an active contour operation on said location of interest to identify the boundary of a feature on said object corresponding to said location of interest.

11. The method of claim 1, wherein sets of markup tags from a plurality of similar objects are mapped to a standardized model to coalesce information from said plurality of similar objects onto said standardized model.

12. The method of claim 11, wherein said coalesced information comprises statistical information derived from accumulated information from a plurality of markup tags for particular locations on said standardized model corresponding to locations of interest designated on said three-dimensional models.

13. The method of claim 11, wherein said plurality of similar objects comprises image sets obtained from the same object at a plurality of different times to provide an empirical time-condition dimension to said markup data.

14. The method of claim 1, wherein said markup tag comprises user-defined information corresponding to a condition assessment of said object provided by a user.

15. The method of claim 14, wherein said markup tag further comprises object data.

16. The method of claim 15, wherein said object data comprises at least one of operating history and maintenance and repair history for said object.

17. The method of claim 14, wherein said object data comprises at least one of a predictive temperature analysis and a predictive stress analysis of said object.

18. The method of claim 1, wherein said inspected objects comprise turbine engine components.

19. The method of claim 1, wherein said inspected objects comprise power generation components.